© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 4467
    Prev
    Next
    INDEX
    Explanations

    specific organelles or structures within a larger system or story

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.67
    ros
    -0.63
    CU
    -0.61
    hement
    -0.60
     PLUS
    -0.60
    rogens
    -0.59
    rosis
    -0.58
     istg
    -0.57
    clerosis
    -0.57
    alam
    -0.57
    POSITIVE LOGITS
     marginally
    1.14
     scratching
    0.93
     kidding
    0.85
     moderately
    0.85
     halfway
    0.82
     mildly
    0.81
     scratched
    0.80
     accessible
    0.79
     partially
    0.78
     slightly
    0.76
    Activations Density 0.058%

    No Known Activations